kth.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Information Visualization for Multi-Source Telecommunications Data Insights: An Interactive GIS-Based Dashboard Solution
KTH, School of Electrical Engineering and Computer Science (EECS).
2024 (English)Independent thesis Advanced level (degree of Master (Two Years)), 20 credits / 30 HE creditsStudent thesisAlternative title
Informationsvisualisering för insikter i flerfaldiga telekommunikationsdata : En interaktiv GIS-baserad dashboardlösning (Swedish)
Abstract [en]

Telecom data with multi-source and spatiotemporal distribution features are extensively used by researchers to characterize human behavior patterns and address various socio-technical issues. However, their large-scale and abstract nature pose challenges for data exploration and understanding. To address this problem, this study uses the Dash framework, combined with parallel computing tools, to develop an interactive GIS-based dashboard. The goal is to efficiently process big data under limited resources and present the spatiotemporal characteristics of telecom data and their potential relationships with other types of data through interactive visualization methods, thus providing researchers with telecom data insights from an information visualization perspective. The developed dashboard contains three main pages, providing spatiotemporal visualizations of telecom activity, telecom interactions, and the relationship between telecom activity and weather data. The dashboard is based on an open-source multi-source telecom dataset of the city of Milan for data analysis. The results show that it can effectively identify data patterns similar to those found in previous studies, as well as specific situations based on the dataset used. Additionally, quantitative performance metrics and heuristic evaluations demonstrate the effectiveness of the dashboard in performance optimization and interface interaction. This study not only provides insights into the dataset used but also offers a reference for the development of lightweight, high-performance dashboards for similar multi-source telecom datasets.

Abstract [sv]

Telekomdata med multi-källor och spatio-temporala distributionsfunktioner används i stor utsträckning av forskare för att karakterisera mänskliga beteendemönster och hantera olika socio-tekniska frågor. Deras storskaliga och abstrakta natur utgör dock utmaningar för datautforskning och förståelse. För att hantera detta problem använder denna studie Dash-ramverket, kombinerat med parallella beräkningsverktyg, för att utveckla en interaktiv GIS-baserad instrument- panel. Målet är att effektivt bearbeta stora datamängder under begränsade resurser och presentera de spatio-temporala egenskaperna hos telekomdata och deras potentiella relationer med andra typer av data genom interaktiva visualiser- ingsmetoder, vilket ger forskare insikter i telekomdata från ett informationsvisualiseringsperspektiv. Den utvecklade instrumentpanelen innehåller tre huvudsidor som tillhandahåller spatio-temporala visualiseringar av telekomaktivitet, telekominteraktioner och förhållandet mellan telekomaktivitet och väderdata. Instrumentpanelen är baserad på en öppen källkod multi-källa telekomdataset från staden Milano för dataanalys. Resultaten visar att den effektivt kan identifiera datamönster som liknar de som hittats i tidigare studier, samt specifika situationer baserat på den använda datasetet. Dessutom visar kvantitativa prestandamått och heuristiska utvärderingar instrumentpanelens effektivitet i prestandaoptimering och gränssnittsinteraktion. Denna studie ger inte bara insikter i den använda datasetet, utan erbjuder också en referens för utveckling av lättviktiga, högpresterande instrumentpaneler för liknande multi-källa telekomdataset.

Place, publisher, year, edition, pages
2024. , p. 39
Series
TRITA-EECS-EX ; 2024:943
Keywords [en]
multi-source telecom data, dashboard visualization, spatiotemporal analysis, parallel computing, community detection
Keywords [sv]
multi-källa telekomdata, instrumentpanelvisualisering, spatio-temporal analys, parallell databehandling, gemenskapsde- tektion
National Category
Computer and Information Sciences
Identifiers
URN: urn:nbn:se:kth:diva-360249OAI: oai:DiVA.org:kth-360249DiVA, id: diva2:1939146
External cooperation
RISE Research Institutes of Sweden
Supervisors
Examiners
Available from: 2025-02-24 Created: 2025-02-20 Last updated: 2025-02-24Bibliographically approved

Open Access in DiVA

fulltext(56527 kB)2445 downloads
File information
File name FULLTEXT02.pdfFile size 56527 kBChecksum SHA-512
571aa4d1ea8fd80180cb4f5cd0d77e2292c0f1d1c42f23d6ad0ec521e7fa30c16b5c9e9b12792094429d12e3af3cceb7f3cc7d7c9421b0091f156e555c71a61b
Type fulltextMimetype application/pdf

By organisation
School of Electrical Engineering and Computer Science (EECS)
Computer and Information Sciences

Search outside of DiVA

GoogleGoogle Scholar
Total: 2445 downloads
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

urn-nbn

Altmetric score

urn-nbn
Total: 522 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf